{"id":431,"date":"2026-02-05T14:03:23","date_gmt":"2026-02-05T13:03:23","guid":{"rendered":"https:\/\/wp.unil.ch\/ecospat\/?page_id=431"},"modified":"2026-02-05T14:16:52","modified_gmt":"2026-02-05T13:16:52","slug":"habitat-suitability-and-distribution-models","status":"publish","type":"page","link":"https:\/\/wp.unil.ch\/ecospat\/habitat-suitability-and-distribution-models\/","title":{"rendered":"Habitat Suitability and Distribution Models"},"content":{"rendered":"\n
\n
\n
\"hsdm-cover.jpg\"<\/figure>\n<\/div>\n\n\n\n
\n

Cambridge University Press<\/a> <\/p>\n\n\n\n

Date published: September 2017<\/p>\n\n\n\n

Authors<\/strong><\/h3>\n\n\n\n

Antoine Guisan<\/a>,  University of Lausanne, Switzerland<\/p>\n\n\n\n

Wilfried Thuiller<\/a> <\/strong>, CNRS, University Grenoble Alpes, France<\/p>\n\n\n\n

Niklaus E. Zimmermann<\/a> <\/strong>, Swiss Federal Research Institute WSL, Switzerland<\/p>\n\n\n\n

With contributions from<\/strong><\/h3>\n\n\n\n

Valeria Di Cola<\/strong>, University of Lausanne (UNIL), Switzerland<\/p>\n\n\n\n

Damien Georges<\/strong>,  CNRS, Universit\u00e9 Grenoble Alpes, France<\/p>\n\n\n\n

Achilleas Psomas<\/strong>, Swiss Federal Research Institute WSL, Switzerland<\/p>\n<\/div>\n<\/div>\n\n\n\n

This book introduces the key stages of niche-based habitat suitability model building, evaluation and prediction required for understanding and predicting future patterns of species and biodiversity.<\/p>\n\n\n\n

Beginning with the main theory behind ecological niches and species distributions, the book proceeds through all major steps of model building, from conceptualization and model training to model evaluation and spatio-temporal predictions.<\/p>\n\n\n\n

Extensive examples using R support graduate students and researchers to quantify ecological niches and predict species distributions with their own data, and help addressing key environmental and conservation problems.<\/p>\n\n\n\n

Reflecting this highly active field of research, the book incorporates the latest developments from informatics and statistics, as well as using data from remote sources such as satellite imagery. This pages contains the codes and supporting material required to run the examples.<\/p>\n\n\n\n

<\/div>\n\n\n
Contents<\/span>Author's Bios<\/span>How to Order<\/span>Downloads<\/span>Errata<\/span>Reviews<\/span><\/div>
\n

Introduction<\/strong><\/h4>\n

1 General content of the book<\/strong>
\n1.1 What is this book about?
\n1.2 How is the book structured?
\n1.3 Why write a textbook with R examples?
\n1.4 What is this book not about?
\n1.5 Why was this book needed?
\n1.6 Who is this book for?
\n1.7 Where can I find supporting material?
\n1.8 What are readers assumed to know already?
\n1.9 How does this book differ from previous ones?
\n1.10 What terminology is used in this book?<\/p>\n

PART I – Overview, Principles, Theory and Assumptions Behind Habitat Suitability Modeling<\/strong><\/h4>\n

2 Overview of the Habitat Suitability Modeling Procedure<\/strong>
\n2.1 The different methodological steps of HSM
\n2.2 The initial conceptual step<\/p>\n

3 What Drives Species Distributions?<\/strong>
\n3.1 The overall context: dispersal, habitat, and biotic filtering
\n3.2 Speciation, dispersal, species pools, and neutral theory
\n3.3 The abiotic environment: habitats and fundamental niches
\n3.4 The biotic environment: species interactions, community assembly, and realized niches
\n3.5 Further discussion of the realized environmental niche and other related niche concepts<\/p>\n

4 From Niche to Distribution: Basic Modeling Principles and Applications<\/strong>
\n4.1 From geographical distribution to niche quantification
\n4.2 From the quantified niche to spatial predictions
\n4.3 From individual species predictions to communities
\n4.4 Main fields of application<\/p>\n

5 Assumptions behind Habitat Suitability Models<\/strong>
\n5.1 Theoretical assumptions behind HSMs
\n5.2 Methodological assumptions<\/p>\n

PART II – Data Acquisition, Sampling Design, and Spatial Scales<\/strong><\/h4>\n

6 Environmental Predictors: Issues of Processing and Selection<\/strong>
\n6.1 Existing environmental databases
\n6.2 Performing simple GIS analyses in R
\n6.3 RS-based predictors
\n6.4 Properties and selection of variables<\/p>\n

7 Species Data: Issues of Acquisition and Design<\/strong>
\n7.1 Existing data and databases
\n7.2 Spatial autocorrelation and pseudo-replicates
\n7.3 Sample size, prevalence, and sample accuracy
\n7.4 Sampling design and data collection
\n7.5 Presence\u2013absence vs. presence-only data<\/p>\n

8 Ecological Scales: Issues of Resolution and Extent<\/strong>
\n8.1 Issues of resolution
\n8.2 Issues of extent<\/p>\n

PART III – Modeling Approaches and Model Calibration<\/strong><\/h4>\n

9 Envelopes and Distance-based Approaches<\/strong>
\n9.1 Concepts
\n9.2 Envelope approaches
\n9.3 Distance-based methods<\/p>\n

10 Regression-based Approaches<\/strong>
\n10.1 Concepts
\n10.2 Generalized linear models
\n10.3 Generalized additive models
\n10.4 Multivariate adaptive regression splines<\/p>\n

11 Classification Approaches and Machine-learning Systems<\/strong>
\n11.1 Concepts
\n11.2 Recursive partitioning
\n11.3 Linear discriminant analysis and extensions
\n11.4 Artificial neural networks<\/p>\n

12 Boosting and Bagging Approaches<\/strong>
\n12.1 Concepts
\n12.2 Random forests
\n12.3 Boosted regression trees<\/p>\n

13 Maximum Entropy<\/strong>
\n13.1 Concepts
\n13.2 Maxent in R<\/p>\n

14 Ensemble Modeling and Modeling Averaging<\/strong><\/p>\n

PART IV – Evaluating Models: Errors and Uncertainty<\/strong><\/h4>\n

15 Measuring Model Accuracy: Which Metrics to Use?<\/strong>
\n15.1 Comparing predicted probabilities of presence to presence\u2013absence observations
\n15.2 Comparing probabilistic predictions to presence-only observations<\/p>\n

16 Assessing Model Performance: Which Data to Use?<\/strong>
\n16.1 Assessment of model fit using resubstitution and randomization
\n16.2 Internal evaluation by resampling
\n16.3 External evaluation (fully independent data)<\/p>\n

PART V – Predictions in Space and Time<\/strong><\/h4>\n

17 Projecting Models in Space and Time<\/strong>
\n17.1 Additional considerations and assumptions when projecting models: analog environment, niche completeness, and niche stability
\n17.2 Projecting species distributions in space
\n17.3 Projecting species in time
\n17.4 Ensemble projections<\/p>\n

PART VI – Data and Tools Used in this Book, with Developed Case Studies<\/strong><\/h4>\n

18 Datasets and Tools Used for the Examples in this Book<\/strong><\/p>\n

19 The Biomod2 Modeling Package Examples<\/strong>
\n19.1 Example 1: HSM of Protea laurifolia<\/em> in South Africa
\n19.2 Example 2: creating diversity maps for the Laurus<\/em> species<\/p>\n

PART VII – Conclusions and Future Perspectives<\/strong><\/p>\n

20 Conclusions and Future Perspectives in Habitat Suitability Modeling<\/strong>
\n20.1 Further progress in HSMs through metagenomics and remote sensing
\n20.2 Point-process models for presence-only data
\n20.3 Hierarchical Bayesian approaches to integrate models at different scales
\n20.4 Ensemble of small models for rarer species
\n20.5 Improving the modeling techniques to fit simple and ensemble HSMs
\n20.6 Multi-species modeling and joint-species distribution modeling
\n20.7 Use of artificial data<\/p>\n

Glossary and Definitions of Terms and Concepts<\/strong><\/h4>\n

Methods, approaches, models, techniques, algorithms
\nENM, SDM, HSM, etc.
\nEnvironment, habitat, niche, niche-biotope duality, and distribution
\nTechnical acronyms for the most commonly used modeling techniques<\/p>\n<\/div>\n

\n

Antoine Guisan<\/strong><\/a>, Universit\u00e9 de Lausanne, Switzerland<\/em><\/p>\n

Antoine Guisan is Professor at the Universit\u00e9 de Lausanne, Switzerland, where he leads the ECOSPAT Spatial Ecology group.<\/p>\n

Wilfried Thuiller<\/strong><\/a>, CNRS, Universit\u00e9 Grenoble Alpes<\/em><\/p>\n

Wilfried Thuiller is a senior scientist at CNRS.<\/p>\n

Niklaus E. Zimmermann<\/strong><\/a>, Swiss Federal Research Institute WSL<\/em><\/p>\n

Niklaus E. Zimmermann is a senior scientist at WSL.<\/p>\n<\/div>\n

\n

The copy of the book can be purchased through Cambridge University Press and other standard distribution channels.<\/p>\n

Order from Cambridge<\/a><\/p>\n

Order from Amazon<\/a><\/p>\n

Order from Barnes & Noble<\/a><\/p>\n<\/div>\n

\n

Links to datasets, code and figures<\/h2>\n
\n
\n

If you use any of these figures in a presentation or lecture, somewhere in your set of slides please add the paragraph: “Some of the figures in this presentation are taken from “Habitat Suitability and Distribution Models: with applications in R. 2017. Cambridge University Press”<\/strong> with permission from the authors: Guisan A., Thuiller W. & Zimmermann N.E.”<\/p>\n

If you wish to use any of these figures in a publication, you must get permission from CUP, and each figure must be accompanied by a similar acknowledgement.<\/p>\n

Data<\/a><\/p>\n

Code Part 2<\/a><\/p>\n

Code Part 3<\/a><\/p>\n

Code Part 4<\/a><\/p>\n

Code Part 5<\/a><\/p>\n

Code Part 6<\/a><\/p>\n

Figures Part 1<\/a><\/p>\n

Figures Part 2<\/a><\/p>\n

Figures Part 3<\/a><\/p>\n

Figures Part 4<\/a><\/p>\n

Figures Part 5<\/a><\/p>\n

Figures Part 6<\/a><\/p>\n<\/div>\n<\/div>\n<\/div>\n

\n

Errata for the 1st Edition, since the 1st printing (September 2017) and not reflected in online version.<\/strong><\/p>\n

This page will include corrections<\/span> (things that are wrong) and updates<\/span> (incorrect now, but not at the time the book was published).<\/p>\n

Please let us know any mistake you would notice in the book (text or code) by sending me an email with the Subject: “ERROR”<\/p>\n

 <\/p>\n

Part 2:<\/strong><\/p>\n

Chapter 6<\/span><\/p>\n

Page 85 (<\/span>Correction<\/span>)<\/span><\/p>\n

Here, we read long-term (30-year normal) annual climate data for precipitation and temperature from the PRISM project (see Section 6.1.2<\/span> 6.2.1<\/del>).<\/span><\/p>\n

 <\/p>\n

Chapter 6<\/span><\/p>\n

Page 86 (<\/span>Correction<\/span>)<\/span><\/p>\n

One frequently used GIS analysis is to import and overlay field sampled species distribution data with environmental predictor layers to later model their habitat suitability (Part III onward). Here, we import a set of distribution data for <\/span>Pinus edulis<\/span><\/em> L., downloaded from GBIF (see Section 7.1<\/span> 6.1.1<\/del>) in July 2014.<\/span><\/p>\n

 <\/p>\n

Chapter 7<\/p>\n

Page 121 (Update<\/span>)<\/p>\n

usa_raster <- rasterize(usa_contin, empty_raster, field=”DRAWSEQ”<\/del>)<\/p>\n

 <\/p>\n

 <\/p>\n

Part 4:<\/strong><\/p>\n

Chapter 16<\/p>\n

Page 290 (Correction<\/span>). Figure legend.<\/p>\n

Figure 16.8 Procedure for the bootstrap approach exemplified on a small number of samples (n = 3)<\/span> sample containing n = 3 observations<\/del>. Each bootstrap dataset contains n observations, sampled with replacement from the original dataset. Each bootstrap dataset is used to obtain an estimate of ? for evaluating predictive models. Adapted from Hastie et al. (2009) and James et al. (2013), with permission.<\/span><\/p>\n<\/div>\n

\n